Chinese Grammatical Error Diagnosis with Graph Convolution Network and Multi-task Learning

no code implementations • AACL (NLP-TEA) 2020 • Yikang Luo, Zuyi Bao, Chen Li, Rui Wang

For the correction subtask, we utilize the masked language model, the seq2seq model and the spelling check model to generate corrections based on the detection results.

Language Modelling Multi-Task Learning +1